使用Python从docx中提取非结构化数据/文本

import docx
import re

doc = docx.Document('file.docx')

extracted_text = ''

for paragraph in doc.paragraphs:
    extracted_text += paragraph.text + '\n'

for table in doc.tables:
    for row in table.rows:
        for cell in row.cells:
            extracted_text += cell.text + '\n'

cleaned_text = re.sub(r'\s+', ' ', extracted_text)  # 清除多余的空格和换行符
data = re.findall(r'pattern', cleaned_text)  # 使用适当的正则表达式模式提取数据

print(data)